Image Based Level-of-Detail Construction for Novel View Synthesis | TU Wien

Information

Publication Type: Master Thesis
Workgroup(s)/Project(s): not specified
Date: 2026
TU Wien Library: AC17849014
Second Supervisor: Diana Marin
Open Access: yes
First Supervisor: Peter Kán
Pages: 76
Keywords: Novel View Synthesis, Level-of-Detail, Anti-Aliasing, Gaussian Splatting, Rendering

Abstract

This thesis presents a coarse-to-fine optimisation method for 3D Gaussian Splatting(3DGS) that constructs a Level of Detail (LoD) hierarchy during optimisation, which can be rendered selectively. By gradually adjusting the resolution, the method reduces computational effort, speeds up optimisation and generates a LoD hierarchy in the process.Based on the sampling rate, defined as the ratio of the resolution at which the model was optimised to that at which it is viewed, a selective rendering method is presented. Selective rendering reduces the number of primitives processed and mitigates aliasing errors, at the cost of increased memory usage on the Graphics Processing Unit (GPU) due to multiple independent LoD levels. The method is evaluated using 3DGS and Elliptical Weighted Average (EWA)-filtering as a basis for comparison on common 360◦ and aerialimage datasets, with a focus on low-resolution renderings and distant viewpoints.The results show that the method speeds up optimisation and reduces the number of processed primitives. Particularly for distant or low-resolution views, images are generated more quickly, and aliasing errors are reduced. At full resolution, the visual quality remains approximately the same as the baseline. Although the method requires additional GPU memory during rendering, it offers a practical approach to faster optimisation of more compact models that are rendered with reduced aliasing.

Additional Files and Images

thesis

Weblinks

BibTeX

@mastersthesis{siemers-2026-ibl,
  title =      "Image Based Level-of-Detail Construction for Novel View
               Synthesis",
  author =     "Ole Siemers",
  year =       "2026",
  abstract =   "This thesis presents a coarse-to-fine optimisation method
               for 3D Gaussian Splatting(3DGS) that constructs a Level of
               Detail (LoD) hierarchy during optimisation, which can be
               rendered selectively. By gradually adjusting the resolution,
               the method reduces computational effort, speeds up
               optimisation and generates a LoD hierarchy in the
               process.Based on the sampling rate, defined as the ratio of
               the resolution at which the model was optimised to that at
               which it is viewed, a selective rendering method is
               presented. Selective rendering reduces the number of
               primitives processed and mitigates aliasing errors, at the
               cost of increased memory usage on the Graphics Processing
               Unit (GPU) due to multiple independent LoD levels. The
               method is evaluated using 3DGS and Elliptical Weighted
               Average (EWA)-filtering as a basis for comparison on common
               360◦ and aerialimage datasets, with a focus on
               low-resolution renderings and distant viewpoints.The results
               show that the method speeds up optimisation and reduces the
               number of processed primitives. Particularly for distant or
               low-resolution views, images are generated more quickly, and
               aliasing errors are reduced. At full resolution, the visual
               quality remains approximately the same as the baseline.
               Although the method requires additional GPU memory during
               rendering, it offers a practical approach to faster
               optimisation of more compact models that are rendered with
               reduced aliasing.",
  pages =      "76",
  address =    "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria",
  school =     "Research Unit of Computer Graphics, Institute of Visual
               Computing and Human-Centered Technology, Faculty of
               Informatics, TU Wien",
  keywords =   "Novel View Synthesis, Level-of-Detail, Anti-Aliasing,
               Gaussian Splatting, Rendering",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2026/siemers-2026-ibl/",
}